Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3839 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3751. Min Act: -0.0000

Data Index: 1467086 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3632. Min Act: -0.0000

Data Index: 1459844 (Python Code)

Max Activating Token Index: 608

Text #2

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.4112. Min Act: -0.0000

Data Index: 1513999 (Python Code)

Max Activating Token Index: 581

Text #3

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3285. Min Act: -0.0000

Data Index: 1411344 (Python Code)

Max Activating Token Index: 502

Text #4

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.4497. Min Act: -0.0000

Data Index: 1610984 (Python Code)

Max Activating Token Index: 359

Text #5

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3853. Min Act: -0.0000

Data Index: 1390996 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1408453 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3827. Min Act: -0.0000

Data Index: 1410732 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3321. Min Act: -0.0000

Data Index: 1636042 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3973. Min Act: -0.0000

Data Index: 1654129 (Python Code)

Max Activating Token Index: 402

Text #10

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3197. Min Act: -0.0000

Data Index: 1645182 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3095. Min Act: -0.0000

Data Index: 1491494 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1367669 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3595. Min Act: -0.0000

Data Index: 1610439 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3813. Min Act: -0.0000

Data Index: 1609157 (Python Code)

Max Activating Token Index: 910

Text #15

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.4204. Min Act: -0.0000

Data Index: 1528039 (Python Code)

Max Activating Token Index: 548

Text #16

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3713. Min Act: -0.0000

Data Index: 1363945 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.3485. Min Act: -0.0000

Data Index: 1530849 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.2948. Min Act: -0.0000

Data Index: 1406007 (Python Code)

Max Activating Token Index: 803

Text #19

Max Range: 2.4497. Min Range: -2.4497

Max Act: 2.2708. Min Act: -0.0000

Data Index: 1375922 (Python Code)

Max Activating Token Index: 447